Skip to main content
Glama

Agent Broker

by io.github.basilalshukaili

send_message

Destructive

Send a message on behalf of an agent's user or an SMB across WhatsApp (free during launch), SMS, email, or voice. Five message types: transactional, reminder, follow_up, notification, marketing. Every send routes through a non-bypassable compliance gate (TCPA, GDPR, CASL, PDPL across 26 jurisdictions) that enforces opt-in consent for marketing/promotional content — marketing without recorded consent is rejected at runtime with a structured compliance_violation receipt. Channel is abstracted: specify intent and recipient; the service selects and falls back across channels.

EXAMPLE USER QUERIES THAT MATCH THIS TOOL: user: "Text the salon I'll be 10 minutes late" -> call send_message({"recipient": {"id_type": "smb_id", "id_value": "smb_xyz"}, "message_type": "notification", "content": {"body": "Running about 10 minutes late for my appointment."}, "preferred_channel": "sms"}) user: "Email the dentist about insurance" -> call send_message({"recipient": {"id_type": "email", "id_value": "front-desk@example-dental.com"}, "message_type": "transactional", "content": {"body": "Do you accept Cigna insurance?"}, "preferred_channel": "email"})

WHEN TO USE: Use to: (a) confirm a booking the agent just made, (b) reply to a customer who messaged the SMB first, (c) follow up on a quote the user requested, (d) send appointment reminders the SMB owes its customer, (e) send marketing messages to recipients who have opted in (with consent_record_id). The gate verifies consent on every send. WHEN NOT TO USE: Do NOT use for OTPs or critical transactional confirmations — use send_transactional_confirmation. Do NOT attempt to send marketing without a consent_record_id pointing at a real opt-in — the gate will reject the send and log a compliance_violation. Do NOT attempt bulk / list-based / drip / cold outreach — those are out of scope and the rate limiter will throttle abuse. COST: from $0.02 per_call_variable (see preview_cost for exact) LATENCY: ~800ms EXECUTION: sync_fast (use get_outcome to retrieve result)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
contentYes
recipientYes
business_idNoOptional stable id for the recipient business. Enables global demand shaping (we rate-limit total inbound across ALL agents so businesses stay responsive instead of blocking us).
send_at_isoNoNOT SUPPORTED YET. We do not schedule messages. Supplying a time more than 2 minutes in the future is REFUSED (reason_code scheduling_not_supported) rather than sent immediately, which is what used to happen. Call send_message at the moment you want delivery, or omit this field.
message_typeYesIntent tag for the message. Five permitted types. 'marketing' is allowed only when paired with a valid consent_record_id; the compliance gate verifies the consent at send time and rejects (compliance_violation receipt) if it's missing, expired, or revoked.
on_behalf_ofNoWho this message is FOR (your end-user's name/label). On WhatsApp this opens a tracked conversation and travels in-message as '#4821 for Sara (via HatchLoop)', so the business knows who it is talking to and their reply is matched back to this exact request instead of guessed. Strongly recommended for two-way channels.
idempotency_keyNoOptional client-supplied key for safe retries. Replaying the same key within 24h returns the original receipt - the operation is NOT re-executed and NOT re-charged.
preferred_channelNoauto

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already signal a mutating, non-idempotent, open-world operation, but the description goes far beyond: it discloses the non-bypassable compliance gate, consent enforcement, channel fallback, rate limiting, scheduling refusal, idempotency replay behavior, cost, latency, and execution model. It even names the failure receipt type (compliance_violation).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-structured with headers, examples, and a front-loaded core statement. There is some repetition of the marketing-consent rule, but it reinforces a critical constraint rather than padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 8-parameter mutation tool with no output schema, the description covers when to use, when not to use, compliance behavior, cost, latency, scheduling limits, and result retrieval via get_outcome. It does not fully specify the success response shape beyond mentioning receipts, so an agent still has to infer part of the return contract.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 63% schema description coverage, the description compensates well: it explains message_type consent coupling, preferred_channel as an abstraction/fallback, send_at_iso refusal behavior, and on_behalf_of rationale. The two examples map recipient and content to realistic values, though parameters like template_id, template_vars, and business_id still rely on schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence names the action (send), the resource (message), the beneficiaries (agent's user or SMB), and the channels (WhatsApp, SMS, email, voice). It clearly distinguishes the tool from send_transactional_confirmation by explicitly excluding OTPs and critical transactional confirmations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides an explicit WHEN TO USE list with five concrete scenarios and a WHEN NOT TO USE section that names the alternative tool and prohibitions. This gives an agent unambiguous routing guidance, including consent requirements and bulk-outreach restrictions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Agent Broker toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0
Disambiguation5/5

Each tool has a clear, distinct purpose with detailed descriptions and explicit WHEN TO USE / WHEN NOT TO USE guidance. Potential overlaps like send_message vs. send_transactional_confirmation are well-differentiated by idempotency and use case, and compliance tools (check_compliance, screen_sanctions, map_trade_restriction) operate on different scopes without ambiguity.

Naming Consistency5/5

All tool names use lowercase snake_case and follow a consistent verb_noun pattern (call_business, check_quota, find_business, send_message, verify_company_record). Even less standard verbs like lookup, map, and mint follow the same structural convention, and there are no mixed casing styles or inconsistent naming patterns.

Tool Count4/5

With 23 tools, this is slightly above the typical 3-15 range, but the breadth of the server's purpose—covering communication, scheduling, compliance, trade screening, and operational utilities—justifies the count. Each tool addresses a distinct capability area, and the set is not bloated with redundant or trivial functions.

Completeness5/5

The tool surface covers the full lifecycle of the broker's domain: business discovery, booking (check, import, schedule), communication (send, receive, read), compliance (pre-flight checks, sanctions, trade restrictions, company verification), and operational support (quota, health, cost preview, key minting, async status/outcome). There are no obvious dead ends or missing critical operations for the stated purpose.

Resources